Commit
•
2023362
1
Parent(s):
f8f176a
update model card README.md
Browse files
README.md
ADDED
@@ -0,0 +1,84 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- generated_from_trainer
|
5 |
+
datasets:
|
6 |
+
- inspec
|
7 |
+
metrics:
|
8 |
+
- f1
|
9 |
+
- precision
|
10 |
+
- recall
|
11 |
+
model-index:
|
12 |
+
- name: bert-finetuned-inspec-3-epochs
|
13 |
+
results:
|
14 |
+
- task:
|
15 |
+
name: Token Classification
|
16 |
+
type: token-classification
|
17 |
+
dataset:
|
18 |
+
name: inspec
|
19 |
+
type: inspec
|
20 |
+
args: extraction
|
21 |
+
metrics:
|
22 |
+
- name: F1
|
23 |
+
type: f1
|
24 |
+
value: 0.28328008519701814
|
25 |
+
- name: Precision
|
26 |
+
type: precision
|
27 |
+
value: 0.26594090202177295
|
28 |
+
- name: Recall
|
29 |
+
type: recall
|
30 |
+
value: 0.3030379746835443
|
31 |
+
---
|
32 |
+
|
33 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
34 |
+
should probably proofread and complete it, then remove this comment. -->
|
35 |
+
|
36 |
+
# bert-finetuned-inspec-3-epochs
|
37 |
+
|
38 |
+
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the inspec dataset.
|
39 |
+
It achieves the following results on the evaluation set:
|
40 |
+
- Loss: 0.2728
|
41 |
+
- F1: 0.2833
|
42 |
+
- Precision: 0.2659
|
43 |
+
- Recall: 0.3030
|
44 |
+
|
45 |
+
## Model description
|
46 |
+
|
47 |
+
More information needed
|
48 |
+
|
49 |
+
## Intended uses & limitations
|
50 |
+
|
51 |
+
More information needed
|
52 |
+
|
53 |
+
## Training and evaluation data
|
54 |
+
|
55 |
+
More information needed
|
56 |
+
|
57 |
+
## Training procedure
|
58 |
+
|
59 |
+
### Training hyperparameters
|
60 |
+
|
61 |
+
The following hyperparameters were used during training:
|
62 |
+
- learning_rate: 5e-05
|
63 |
+
- train_batch_size: 8
|
64 |
+
- eval_batch_size: 8
|
65 |
+
- seed: 0
|
66 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
67 |
+
- lr_scheduler_type: linear
|
68 |
+
- num_epochs: 3
|
69 |
+
|
70 |
+
### Training results
|
71 |
+
|
72 |
+
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall |
|
73 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|:------:|
|
74 |
+
| 0.3338 | 1.0 | 125 | 0.2837 | 0.1401 | 0.1510 | 0.1306 |
|
75 |
+
| 0.2575 | 2.0 | 250 | 0.2658 | 0.2183 | 0.2519 | 0.1927 |
|
76 |
+
| 0.2259 | 3.0 | 375 | 0.2728 | 0.2833 | 0.2659 | 0.3030 |
|
77 |
+
|
78 |
+
|
79 |
+
### Framework versions
|
80 |
+
|
81 |
+
- Transformers 4.19.2
|
82 |
+
- Pytorch 1.11.0+cu113
|
83 |
+
- Datasets 2.2.1
|
84 |
+
- Tokenizers 0.12.1
|